knitr::opts_chunk$set(echo = TRUE, message = FALSE, warning = FALSE)
library(tidyverse)
library(here)
library(sf) # install.packages('sf')
library(tmap)
### install.packages('tmap')
### update.packages(ask = FALSE)
cmd-shift-enter shortcut for running the current code chunk
cmd-option-i shortcut for creating a code chunk
sf_trees <- read_csv(here('data', 'sf_trees', 'sf_trees.csv'),
show_col_types = FALSE)
names(sf_trees) to get the names of the columns summary(sf_trees) to get an idea about the data in each of those columns
Example 1: Find counts of observation by legal_status & wrangle a bit.
### method 1: group_by() %>% summarize()
sf_trees %>%
group_by(legal_status) %>%
summarize(tree_count = n())
## # A tibble: 10 × 2
## legal_status tree_count
## <chr> <int>
## 1 DPW Maintained 141725
## 2 Landmark tree 42
## 3 Permitted Site 39732
## 4 Planning Code 138.1 required 971
## 5 Private 163
## 6 Property Tree 316
## 7 Section 143 230
## 8 Significant Tree 1648
## 9 Undocumented 8106
## 10 <NA> 54
### method 2: different way plus a few new functions
### store stuff in an object this time
### highlight code and press command+enter
top_5_status <- sf_trees %>%
count(legal_status) %>%
drop_na(legal_status) %>%
rename(tree_count = n) %>%
relocate(tree_count) %>%
slice_max(tree_count, n = 5) %>%
arrange(desc(tree_count))
### drop_na() would get rid of a row with NA in any column. we just want NA in legal_status column not for example na in a date column
### rename column from n to tree_count
### relocates that column to the front of the dataframe
### look at all values of tree_count and slice out the highest ones. in this case the top 5
### arrange(tree_count) does lowest to highest
### to get highest to lowest: arrange(-tree_count) OR arrange(desc(tree_count))
Make a graph of the top 5 from above:
ggplot(data = top_5_status, aes(x = fct_reorder(legal_status, tree_count), y = tree_count)) +
geom_col(fill = 'darkgreen') +
labs(x = 'Legal status', y = 'Tree count') +
coord_flip() +
theme_minimal()
### to change the order of the columns: fct_reorder(legal_status, tree_count) to order the trees by tree_count. if wanted largest to smallest, then do -tree_count
Example 2: Only going to keep observations where legal status is “Permitted Site” and caretaker is “MTA”, and store as permitted_data_df
shift-cmd-c to comment/uncomment quickly
# sf_trees$legal_status %>% unique()
# unique(sf_trees$caretaker)
permitted_data_df <- sf_trees %>%
filter(legal_status == 'Permitted Site', caretaker == 'MTA')
### can also use & instead of ,
### use | as or
### filter(legal_status %in% c('Permitted Site', 'Private') & caretaker == 'MTA')
Example 3: Only keep Blackwood Acacia trees, and then only keep columns legal_status, date, latitude, longitude and store as blackwood_acacia_df
blackwood_acacia_df <- sf_trees %>%
filter(str_detect(species, 'Blackwood Acacia')) %>%
select(legal_status, date, lat = latitude, lon = longitude)
### rename column to lat
### Make a little graph of locations
ggplot(data = blackwood_acacia_df, aes(x = lon, y = lat)) +
geom_point(color = 'darkgreen')
### doesn't know this is spatial data yet
Example 4: use tidyr:separate()
sf_trees_sep <- sf_trees %>%
separate(species, into = c('spp_scientific', 'spp_common'), sep = ' :: ')
Example 5: use tidyr::unite()
ex_5 <- sf_trees %>%
unite('id_status', tree_id, legal_status, sep = '_COOL_')
Step 1: convert the lat/lon to spatial point, st_as_sf()
### sf is simple features object
### it knows this is a spacial object with st_as_sf
blackwood_acacia_sf <- blackwood_acacia_df %>%
drop_na(lat, lon) %>%
st_as_sf(coords = c('lon', 'lat'))
### we need to tell R what the coordinate reference system is
st_crs(blackwood_acacia_sf) <- 4326
ggplot(data = blackwood_acacia_sf) +
geom_sf(color = 'darkgreen') +
theme_minimal()
Read in the SF shapefile and add to map
sf_map <- read_sf(here('data', 'sf_map', 'tl_2017_06075_roads.shp'))
### read in the shapefile
### st_crs(sf_map)
sf_map_transform <- st_transform(sf_map, 4326)
ggplot(data = sf_map_transform) +
geom_sf()
Combine the maps!
ggplot() +
geom_sf(data = sf_map, #layers build. this layer will be underneath
size = .1, # make size of lines smaller
color = 'darkgrey') +
geom_sf(data = blackwood_acacia_sf,
color = 'red',
size = 0.5) +
theme_void() +
labs(title = 'Blackwood acacias in SF')
tmap_mode('view')
tm_shape(blackwood_acacia_sf) +
tm_dots()